metadata
base_model: microsoft/git-large-r-coco
datasets:
- imagefolder
library_name: transformers
license: mit
tags:
- generated_from_trainer
model-index:
- name: git-large-r-coco-IDB_ADv1_COCOv6-r
results: []
git-large-r-coco-IDB_ADv1_COCOv6-r
This model is a fine-tuned version of microsoft/git-large-r-coco on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.4382
- Meteor Score: {'meteor': 0.6824076148140416}
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 12
- total_train_batch_size: 96
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 8
- num_epochs: 80
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Meteor Score |
|---|---|---|---|---|
| 27.8843 | 5.0 | 5 | 2.2779 | {'meteor': 0.42881843961238963} |
| 26.945 | 10.0 | 10 | 2.0505 | {'meteor': 0.501440106486018} |
| 23.3885 | 15.0 | 15 | 1.7544 | {'meteor': 0.5479716568094775} |
| 19.76 | 20.0 | 20 | 1.4758 | {'meteor': 0.5955711928745901} |
| 16.4691 | 25.0 | 25 | 1.2338 | {'meteor': 0.6204550135358564} |
| 13.6022 | 30.0 | 30 | 1.0289 | {'meteor': 0.6345912561041426} |
| 11.1047 | 35.0 | 35 | 0.8510 | {'meteor': 0.6561421187912199} |
| 9.0826 | 40.0 | 40 | 0.7206 | {'meteor': 0.6457048205815358} |
| 7.4764 | 45.0 | 45 | 0.6199 | {'meteor': 0.6633570447161818} |
| 6.2926 | 50.0 | 50 | 0.5478 | {'meteor': 0.6755789926464999} |
| 5.4384 | 55.0 | 55 | 0.5033 | {'meteor': 0.6715844748121845} |
| 4.8435 | 60.0 | 60 | 0.4708 | {'meteor': 0.6776793022097405} |
| 4.4628 | 65.0 | 65 | 0.4527 | {'meteor': 0.6824716486996648} |
| 4.2404 | 70.0 | 70 | 0.4427 | {'meteor': 0.6877583553949453} |
| 4.1204 | 75.0 | 75 | 0.4396 | {'meteor': 0.683676455787374} |
| 4.0752 | 80.0 | 80 | 0.4382 | {'meteor': 0.6824076148140416} |
Framework versions
- Transformers 4.46.1
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.20.2